© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 18455
    Prev
    Next
    INDEX
    Explanations

    verbs in past tense that indicate completion or accomplishment

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs and auxiliary verbs indicating uncertainty or potential actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Submission
    -0.68
     Brett
    -0.63
     millenn
    -0.63
     اÙĦ
    -0.62
     Bastard
    -0.60
     Reich
    -0.60
     Provision
    -0.60
     Technician
    -0.60
     Imam
    -0.59
     Claus
    -0.59
    POSITIVE LOGITS
    lled
    1.17
    adic
    1.15
    eded
    1.11
    ties
    1.11
    ement
    1.10
    aned
    1.09
    abal
    1.08
    ering
    1.08
    ched
    1.08
    athy
    1.07
    Activations Density 0.930%

    No Known Activations